End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: llama3.1
 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- barc0/transduction_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3
 model-index:
 - name: barc-llama3.1-8b-instruct-fft-transduction-gpt4omini10k_lr1e-5_epoch1__
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # barc-llama3.1-8b-instruct-fft-transduction-gpt4omini10k_lr1e-5_epoch1__
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the barc0/transduction_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0932
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.09319383651018143,
+    "eval_runtime": 128.8246,
+    "eval_samples": 5105,
+    "eval_samples_per_second": 39.628,
+    "eval_steps_per_second": 1.242,
     "total_flos": 2.244031216091136e+16,
     "train_loss": 0.12603967764267796,
     "train_runtime": 1049.273,

config.json

@@ -35,6 +35,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.09319383651018143,
+    "eval_runtime": 128.8246,
+    "eval_samples": 5105,
+    "eval_samples_per_second": 39.628,
+    "eval_steps_per_second": 1.242
+}

runs/Sep25_15-48-00_instance-20240925-140811/events.out.tfevents.1727280797.instance-20240925-140811.26163.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f21ccd5cfb66adee95f8ffe5e8b2ca06b41912d720a7b46dc7f381b11d0d83
+size 354